小型医疗知识图谱项目--基于医疗知识图谱的自动问答

• chatbot_graph.py：问答程序脚本

  • question_classifier.py：问句类型分类脚本
  • question_parser.py：问句解析脚本
  • answer_search.py 定制化answer脚本

总结

整体的逻辑就是对我们的提问句中的关键词，可以完成提问类型的划分，我们在根据划分的类型构造对应的neo4j的sql查询语句，最终根据查询回来的语句完成answer的构造，最终将答案返回回去。

核心技术：AC自动机、neo4j的查询

chatbot_graph.py

这个是问答系统开启的脚本，其实我们从从__init__中可以知道，我们先对用户输入的问题进行分类，然后我们在对分类的结果进行解析，解析完成我们将解析的结果放入到答案搜寻中，我们就能得到最终的答案，从neo4j中返回了答案，直接返回，如没有返回任何的答案(问题超纲)，直接使用预先准备好的答案即可。

from question_classifier import *
from question_parser import *
from answer_search import *

'''问答类'''
class ChatBotGraph:
    def __init__(self):
        self.classifier = QuestionClassifier()
        self.parser = QuestionPaser()
        self.searcher = AnswerSearcher()

    def chat_main(self, sent):
        answer = '您好，我是小勇医药智能助理，希望可以帮到您。如果没答上来，可联系https://liuhuanyong.github.io/。祝您身体棒棒！'
        # 问题分类
        res_classify = self.classifier.classify(sent)
        if not res_classify:
            return answer
        # 分类结果解析
        res_sql = self.parser.parser_main(res_classify)
        # 解析结果搜索答案
        final_answers = self.searcher.search_main(res_sql)
        if not final_answers:
            return answer
        else:
            return '\n'.join(final_answers)

if __name__ == '__main__':
    handler = ChatBotGraph()
    while 1:
        question = input('用户:')
        answer = handler.chat_main(question)
        print('小勇:', answer)

question_classifier.py

• 这个代码的核心就是将我们的提问的句子，转化成对应搜索的实际的类别信息
  • 例：白血病是啥意思？-- {question_types:[A,B,C等]，args :[{"白血病":disease},{等}]}

import os
import ahocorasick

class QuestionClassifier:
    def __init__(self):
        cur_dir = '/'.join(os.path.abspath(__file__).split('/')[:-1])
        #　特征词路径
        self.disease_path = os.path.join(cur_dir, 'dict/disease.txt')
        self.department_path = os.path.join(cur_dir, 'dict/department.txt')
        self.check_path = os.path.join(cur_dir, 'dict/check.txt')
        self.drug_path = os.path.join(cur_dir, 'dict/drug.txt')
        self.food_path = os.path.join(cur_dir, 'dict/food.txt')
        self.producer_path = os.path.join(cur_dir, 'dict/producer.txt')
        self.symptom_path = os.path.join(cur_dir, 'dict/symptom.txt')
        self.deny_path = os.path.join(cur_dir, 'dict/deny.txt')
        # 加载特征词
        self.disease_wds= [i.strip() for i in open(self.disease_path,"r",encoding="utf-8") if i.strip()]
        self.department_wds= [i.strip() for i in open(self.department_path,"r",encoding="utf-8") if i.strip()]
        self.check_wds= [i.strip() for i in open(self.check_path,"r",encoding="utf-8") if i.strip()]
        self.drug_wds= [i.strip() for i in open(self.drug_path,"r",encoding="utf-8") if i.strip()]
        self.food_wds= [i.strip() for i in open(self.food_path,"r",encoding="utf-8") if i.strip()]
        self.producer_wds= [i.strip() for i in open(self.producer_path,"r",encoding="utf-8") if i.strip()]
        self.symptom_wds= [i.strip() for i in open(self.symptom_path,"r",encoding="utf-8") if i.strip()]
        
        # 在neo4j数据入库的时候有个export_data方法，在那个方法中我们将数据整理成txt,现在读取文件构造专业领域词汇
        self.region_words = set(self.department_wds + self.disease_wds + self.check_wds + self.drug_wds + self.food_wds + self.producer_wds + self.symptom_wds)
        self.deny_words = [i.strip() for i in open(self.deny_path,"r",encoding="utf-8") if i.strip()]
        
        # 构造领域actree，这个地方是使用ahocorasick这个构建状态机，可以进行多模态搜索
        self.region_tree = self.build_actree(list(self.region_words))
        
        # 构建词典
        # 在领域词汇中添加对应的类型
        self.wdtype_dict = self.build_wdtype_dict()
        
        # 构建大量常见的提出疑问的词语集合
        # 这些词语是在拆分提问中的关键词，然后和我们指定类型挂钩
        # 例如：self.check_words(self.symptom_qwds, question)---disease_symptom
        self.symptom_qwds = ['症状', '表征', '现象', '症候', '表现']
        self.cause_qwds = ['原因','成因', '为什么', '怎么会', '怎样才', '咋样才', '怎样会', '如何会', '为啥', '为何', '如何才会', '怎么才会', '会导致', '会造成']
        self.acompany_qwds = ['并发症', '并发', '一起发生', '一并发生', '一起出现', '一并出现', '一同发生', '一同出现', '伴随发生', '伴随', '共现']
        self.food_qwds = ['饮食', '饮用', '吃', '食', '伙食', '膳食', '喝', '菜' ,'忌口', '补品', '保健品', '食谱', '菜谱', '食用', '食物','补品']
        self.drug_qwds = ['药', '药品', '用药', '胶囊', '口服液', '炎片']
        self.prevent_qwds = ['预防', '防范', '抵制', '抵御', '防止','躲避','逃避','避开','免得','逃开','避开','避掉','躲开','躲掉','绕开',
                             '怎样才能不', '怎么才能不', '咋样才能不','咋才能不', '如何才能不',
                             '怎样才不', '怎么才不', '咋样才不','咋才不', '如何才不',
                             '怎样才可以不', '怎么才可以不', '咋样才可以不', '咋才可以不', '如何可以不',
                             '怎样才可不', '怎么才可不', '咋样才可不', '咋才可不', '如何可不']
        self.lasttime_qwds = ['周期', '多久', '多长时间', '多少时间', '几天', '几年', '多少天', '多少小时', '几个小时', '多少年']
        self.cureway_qwds = ['怎么治疗', '如何医治', '怎么医治', '怎么治', '怎么医', '如何治', '医治方式', '疗法', '咋治', '怎么办', '咋办', '咋治']
        self.cureprob_qwds = ['多大概率能治好', '多大几率能治好', '治好希望大么', '几率', '几成', '比例', '可能性', '能治', '可治', '可以治', '可以医']
        self.easyget_qwds = ['易感人群', '容易感染', '易发人群', '什么人', '哪些人', '感染', '染上', '得上']
        self.check_qwds = ['检查', '检查项目', '查出', '检查', '测出', '试出']
        self.belong_qwds = ['属于什么科', '属于', '什么科', '科室']
        self.cure_qwds = ['治疗什么', '治啥', '治疗啥', '医治啥', '治愈啥', '主治啥', '主治什么', '有什么用', '有何用', '用处', '用途',
                          '有什么好处', '有什么益处', '有何益处', '用来', '用来做啥', '用来作甚', '需要', '要']

        print('model init finished ......')

        return

    '''分类主函数'''
    # 核心思路
    def classify(self, question):
        data = {}
        
        # 收集提问中的关键词和关键词的类型
        medical_dict = self.check_medical(question)
        if not medical_dict:
            return {}
        data['args'] = medical_dict
        
        #收集问句当中所涉及到的实体类型
        types = []
        for type_ in medical_dict.values():
            types += type_
        question_type = 'others'

        question_types = []

        # 检查我们的句子，对我们上面准备好的词典进行扫描，并且对类型进行指定，
        # 将查询到的问题类型加入到question_type的列表中
        # 中间可能存在既是疾病又是症状这样的特例，所以我们需要都进行考虑
        # 症状
        if self.check_words(self.symptom_qwds, question) and ('disease' in types):
            question_type = 'disease_symptom'
            question_types.append(question_type)

        if self.check_words(self.symptom_qwds, question) and ('symptom' in types):
            question_type = 'symptom_disease'
            question_types.append(question_type)

        # 原因
        if self.check_words(self.cause_qwds, question) and ('disease' in types):
            question_type = 'disease_cause'
            question_types.append(question_type)
        # 并发症
        if self.check_words(self.acompany_qwds, question) and ('disease' in types):
            question_type = 'disease_acompany'
            question_types.append(question_type)

        # 推荐食品
        if self.check_words(self.food_qwds, question) and 'disease' in types:
            deny_status = self.check_words(self.deny_words, question)
            if deny_status:
                question_type = 'disease_not_food'
            else:
                question_type = 'disease_do_food'
            question_types.append(question_type)

        #已知食物找疾病
        if self.check_words(self.food_qwds+self.cure_qwds, question) and 'food' in types:
            deny_status = self.check_words(self.deny_words, question)
            if deny_status:
                question_type = 'food_not_disease'
            else:
                question_type = 'food_do_disease'
            question_types.append(question_type)

        # 推荐药品
        if self.check_words(self.drug_qwds, question) and 'disease' in types:
            question_type = 'disease_drug'
            question_types.append(question_type)

        # 药品治啥病
        if self.check_words(self.cure_qwds, question) and 'drug' in types:
            question_type = 'drug_disease'
            question_types.append(question_type)

        # 疾病接受检查项目
        if self.check_words(self.check_qwds, question) and 'disease' in types:
            question_type = 'disease_check'
            question_types.append(question_type)

        # 已知检查项目查相应疾病
        if self.check_words(self.check_qwds+self.cure_qwds, question) and 'check' in types:
            question_type = 'check_disease'
            question_types.append(question_type)

        #　症状防御
        if self.check_words(self.prevent_qwds, question) and 'disease' in types:
            question_type = 'disease_prevent'
            question_types.append(question_type)

        # 疾病医疗周期
        if self.check_words(self.lasttime_qwds, question) and 'disease' in types:
            question_type = 'disease_lasttime'
            question_types.append(question_type)

        # 疾病治疗方式
        if self.check_words(self.cureway_qwds, question) and 'disease' in types:
            question_type = 'disease_cureway'
            question_types.append(question_type)

        # 疾病治愈可能性
        if self.check_words(self.cureprob_qwds, question) and 'disease' in types:
            question_type = 'disease_cureprob'
            question_types.append(question_type)

        # 疾病易感染人群
        if self.check_words(self.easyget_qwds, question) and 'disease' in types :
            question_type = 'disease_easyget'
            question_types.append(question_type)

        # 若没有查到相关的外部查询信息，那么则将该疾病的描述信息返回
        if question_types == [] and 'disease' in types:
            question_types = ['disease_desc']

        # 若没有查到相关的外部查询信息，那么则将该疾病的描述信息返回
        if question_types == [] and 'symptom' in types:
            question_types = ['symptom_disease']

        # 将多个分类结果进行合并处理，组装成一个字典
        data['question_types'] = question_types
		
        # 最后在数据字典中包含两个信息：question_types = [A,B,C等]，args = [{"白血病":disease},{等}]
        return data

    '''构造词对应的类型'''
    def build_wdtype_dict(self):
        wd_dict = dict()
        for wd in self.region_words:
            wd_dict[wd] = []
            if wd in self.disease_wds:
                wd_dict[wd].append('disease')
            if wd in self.department_wds:
                wd_dict[wd].append('department')
            if wd in self.check_wds:
                wd_dict[wd].append('check')
            if wd in self.drug_wds:
                wd_dict[wd].append('drug')
            if wd in self.food_wds:
                wd_dict[wd].append('food')
            if wd in self.symptom_wds:
                wd_dict[wd].append('symptom')
            if wd in self.producer_wds:
                wd_dict[wd].append('producer')
        return wd_dict

    '''构造actree，加速过滤'''
    def build_actree(self, wordlist):
        # 制作AC状态机的过程
        actree = ahocorasick.Automaton()
        for index, word in enumerate(wordlist):
            actree.add_word(word, (index, word))
        actree.make_automaton()
        return actree

    '''问句过滤'''
    def check_medical(self, question):
        '''
        这个函数的主要作用是：
        '''
        region_wds = []
        # 将我们输入的句子和我们的领域单词进行一一对比，提取出来击中的单词，也就是后面搜索的关键词
        for i in self.region_tree.iter(question):
            wd = i[1][1]
            region_wds.append(wd)
        stop_wds = []
        # 对包含类的关键词进行过滤，白血病和白血病综合征，我们发现白血病综合征包含白血病，我们将白血病过滤掉
        for wd1 in region_wds:
            for wd2 in region_wds:
                if wd1 in wd2 and wd1 != wd2:
                    stop_wds.append(wd1)
        final_wds = [i for i in region_wds if i not in stop_wds]
        
        # 将击中的单词和所属类别放入字典中
        final_dict = {i:self.wdtype_dict.get(i) for i in final_wds}

        return final_dict

    '''基于特征词进行分类'''
    def check_words(self, wds, sent):
        # 就是str1 in str2 的问题
        for wd in wds:
            if wd in sent:
                return True
        return False


if __name__ == '__main__':
    handler = QuestionClassifier()
    while 1:
        question = input('input an question:')
        data = handler.classify(question)
        print(data)

question_parser.py

• 其实这个函数就是一个桥梁，将我们之前从问题语句中得到的查询类型和词组，转化成能执行的neo4j_sql

# 没啥技术含量，if无限对应即可
class QuestionPaser:

    '''构建实体节点'''
    def build_entitydict(self, args):
        entity_dict = {}
        for arg, types in args.items():
            for type in types:
                if type not in entity_dict:
                    entity_dict[type] = [arg]
                else:
                    entity_dict[type].append(arg)
        return entity_dict

    '''解析主函数'''
    def parser_main(self, res_classify):
        args = res_classify['args']
        entity_dict = self.build_entitydict(args)
        question_types = res_classify['question_types']
        sqls = []
        
        # 对于不同的类型，我们映射到不同的sql上去，同时将我们的实体节点嵌入进去，构成一条可执行的neo4j_sql语句
        # 多个question_type，最终形成的就是一个neo4j_sql_list的列表
        for question_type in question_types:
            sql_ = {}
            sql_['question_type'] = question_type
            sql = []
            if question_type == 'disease_symptom':
                sql = self.sql_transfer(question_type, entity_dict.get('disease'))

            elif question_type == 'symptom_disease':
                sql = self.sql_transfer(question_type, entity_dict.get('symptom'))

            elif question_type == 'disease_cause':
                sql = self.sql_transfer(question_type, entity_dict.get('disease'))

            elif question_type == 'disease_acompany':
                sql = self.sql_transfer(question_type, entity_dict.get('disease'))

            elif question_type == 'disease_not_food':
                sql = self.sql_transfer(question_type, entity_dict.get('disease'))

            elif question_type == 'disease_do_food':
                sql = self.sql_transfer(question_type, entity_dict.get('disease'))

            elif question_type == 'food_not_disease':
                sql = self.sql_transfer(question_type, entity_dict.get('food'))

            elif question_type == 'food_do_disease':
                sql = self.sql_transfer(question_type, entity_dict.get('food'))

            elif question_type == 'disease_drug':
                sql = self.sql_transfer(question_type, entity_dict.get('disease'))

            elif question_type == 'drug_disease':
                sql = self.sql_transfer(question_type, entity_dict.get('drug'))

            elif question_type == 'disease_check':
                sql = self.sql_transfer(question_type, entity_dict.get('disease'))

            elif question_type == 'check_disease':
                sql = self.sql_transfer(question_type, entity_dict.get('check'))

            elif question_type == 'disease_prevent':
                sql = self.sql_transfer(question_type, entity_dict.get('disease'))

            elif question_type == 'disease_lasttime':
                sql = self.sql_transfer(question_type, entity_dict.get('disease'))

            elif question_type == 'disease_cureway':
                sql = self.sql_transfer(question_type, entity_dict.get('disease'))

            elif question_type == 'disease_cureprob':
                sql = self.sql_transfer(question_type, entity_dict.get('disease'))

            elif question_type == 'disease_easyget':
                sql = self.sql_transfer(question_type, entity_dict.get('disease'))

            elif question_type == 'disease_desc':
                sql = self.sql_transfer(question_type, entity_dict.get('disease'))

            if sql:
                sql_['sql'] = sql

                sqls.append(sql_)

        return sqls

    '''针对不同的问题，分开进行处理'''
    def sql_transfer(self, question_type, entities):
        if not entities:
            return []

        # 查询语句
        sql = []
        # 查询疾病的原因
        if question_type == 'disease_cause':
            sql = ["MATCH (m:Disease) where m.name = '{0}' return m.name, m.cause".format(i) for i in entities]

        # 查询疾病的防御措施
        elif question_type == 'disease_prevent':
            sql = ["MATCH (m:Disease) where m.name = '{0}' return m.name, m.prevent".format(i) for i in entities]

        # 查询疾病的持续时间
        elif question_type == 'disease_lasttime':
            sql = ["MATCH (m:Disease) where m.name = '{0}' return m.name, m.cure_lasttime".format(i) for i in entities]

        # 查询疾病的治愈概率
        elif question_type == 'disease_cureprob':
            sql = ["MATCH (m:Disease) where m.name = '{0}' return m.name, m.cured_prob".format(i) for i in entities]

        # 查询疾病的治疗方式
        elif question_type == 'disease_cureway':
            sql = ["MATCH (m:Disease) where m.name = '{0}' return m.name, m.cure_way".format(i) for i in entities]

        # 查询疾病的易发人群
        elif question_type == 'disease_easyget':
            sql = ["MATCH (m:Disease) where m.name = '{0}' return m.name, m.easy_get".format(i) for i in entities]

        # 查询疾病的相关介绍
        elif question_type == 'disease_desc':
            sql = ["MATCH (m:Disease) where m.name = '{0}' return m.name, m.desc".format(i) for i in entities]

        # 查询疾病有哪些症状
        elif question_type == 'disease_symptom':
            sql = ["MATCH (m:Disease)-[r:has_symptom]->(n:Symptom) where m.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]

        # 查询症状会导致哪些疾病
        elif question_type == 'symptom_disease':
            sql = ["MATCH (m:Disease)-[r:has_symptom]->(n:Symptom) where n.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]

        # 查询疾病的并发症
        elif question_type == 'disease_acompany':
            sql1 = ["MATCH (m:Disease)-[r:acompany_with]->(n:Disease) where m.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]
            sql2 = ["MATCH (m:Disease)-[r:acompany_with]->(n:Disease) where n.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]
            sql = sql1 + sql2
        # 查询疾病的忌口
        elif question_type == 'disease_not_food':
            sql = ["MATCH (m:Disease)-[r:no_eat]->(n:Food) where m.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]

        # 查询疾病建议吃的东西
        elif question_type == 'disease_do_food':
            sql1 = ["MATCH (m:Disease)-[r:do_eat]->(n:Food) where m.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]
            sql2 = ["MATCH (m:Disease)-[r:recommand_eat]->(n:Food) where m.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]
            sql = sql1 + sql2

        # 已知忌口查疾病
        elif question_type == 'food_not_disease':
            sql = ["MATCH (m:Disease)-[r:no_eat]->(n:Food) where n.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]

        # 已知推荐查疾病
        elif question_type == 'food_do_disease':
            sql1 = ["MATCH (m:Disease)-[r:do_eat]->(n:Food) where n.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]
            sql2 = ["MATCH (m:Disease)-[r:recommand_eat]->(n:Food) where n.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]
            sql = sql1 + sql2

        # 查询疾病常用药品－药品别名记得扩充
        elif question_type == 'disease_drug':
            sql1 = ["MATCH (m:Disease)-[r:common_drug]->(n:Drug) where m.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]
            sql2 = ["MATCH (m:Disease)-[r:recommand_drug]->(n:Drug) where m.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]
            sql = sql1 + sql2

        # 已知药品查询能够治疗的疾病
        elif question_type == 'drug_disease':
            sql1 = ["MATCH (m:Disease)-[r:common_drug]->(n:Drug) where n.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]
            sql2 = ["MATCH (m:Disease)-[r:recommand_drug]->(n:Drug) where n.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]
            sql = sql1 + sql2
        # 查询疾病应该进行的检查
        elif question_type == 'disease_check':
            sql = ["MATCH (m:Disease)-[r:need_check]->(n:Check) where m.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]

        # 已知检查查询疾病
        elif question_type == 'check_disease':
            sql = ["MATCH (m:Disease)-[r:need_check]->(n:Check) where n.name = '{0}' return m.name, r.name, n.name".format(i) for i in entities]

        return sql

if __name__ == '__main__':
    handler = QuestionPaser()

answer_search.py

• 这个部分就是执行上面拿到的neo4j_sql_list语句列表，然后对其中的sql执行，最后对结果进行定制化封装

# 和QuestionPaser一样，就是对neo4j返回的结果，进行定制化封装，比较简单
from py2neo import Graph

class AnswerSearcher:
    def __init__(self):
        self.graph = Graph("http://localhost:7474", auth=("neo4j","waws"))
        self.num_limit = 20

    '''执行cypher查询，并返回相应结果'''
    def search_main(self, sqls):
        final_answers = []
        for sql_ in sqls:
            question_type = sql_['question_type']
            queries = sql_['sql']
            answers = []
            for query in queries:
                ress = self.graph.run(query).data()
                answers += ress
            final_answer = self.answer_prettify(question_type, answers)
            if final_answer:
                final_answers.append(final_answer)
        return final_answers

    '''根据对应的qustion_type，调用相应的回复模板'''
    def answer_prettify(self, question_type, answers):
        final_answer = []
        if not answers:
            return ''
        if question_type == 'disease_symptom':
            desc = [i['n.name'] for i in answers]
            subject = answers[0]['m.name']
            final_answer = '{0}的症状包括：{1}'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'symptom_disease':
            desc = [i['m.name'] for i in answers]
            subject = answers[0]['n.name']
            final_answer = '症状{0}可能染上的疾病有：{1}'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'disease_cause':
            desc = [i['m.cause'] for i in answers]
            subject = answers[0]['m.name']
            final_answer = '{0}可能的成因有：{1}'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'disease_prevent':
            desc = [i['m.prevent'] for i in answers]
            subject = answers[0]['m.name']
            final_answer = '{0}的预防措施包括：{1}'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'disease_lasttime':
            desc = [i['m.cure_lasttime'] for i in answers]
            subject = answers[0]['m.name']
            final_answer = '{0}治疗可能持续的周期为：{1}'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'disease_cureway':
            desc = [';'.join(i['m.cure_way']) for i in answers]
            subject = answers[0]['m.name']
            final_answer = '{0}可以尝试如下治疗：{1}'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'disease_cureprob':
            desc = [i['m.cured_prob'] for i in answers]
            subject = answers[0]['m.name']
            final_answer = '{0}治愈的概率为（仅供参考）：{1}'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'disease_easyget':
            desc = [i['m.easy_get'] for i in answers]
            subject = answers[0]['m.name']

            final_answer = '{0}的易感人群包括：{1}'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'disease_desc':
            desc = [i['m.desc'] for i in answers]
            subject = answers[0]['m.name']
            final_answer = '{0},熟悉一下：{1}'.format(subject,  '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'disease_acompany':
            desc1 = [i['n.name'] for i in answers]
            desc2 = [i['m.name'] for i in answers]
            subject = answers[0]['m.name']
            desc = [i for i in desc1 + desc2 if i != subject]
            final_answer = '{0}的症状包括：{1}'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'disease_not_food':
            desc = [i['n.name'] for i in answers]
            subject = answers[0]['m.name']
            final_answer = '{0}忌食的食物包括有：{1}'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'disease_do_food':
            do_desc = [i['n.name'] for i in answers if i['r.name'] == '宜吃']
            recommand_desc = [i['n.name'] for i in answers if i['r.name'] == '推荐食谱']
            subject = answers[0]['m.name']
            final_answer = '{0}宜食的食物包括有：{1}\n推荐食谱包括有：{2}'.format(subject, ';'.join(list(set(do_desc))[:self.num_limit]), ';'.join(list(set(recommand_desc))[:self.num_limit]))

        elif question_type == 'food_not_disease':
            desc = [i['m.name'] for i in answers]
            subject = answers[0]['n.name']
            final_answer = '患有{0}的人最好不要吃{1}'.format('；'.join(list(set(desc))[:self.num_limit]), subject)

        elif question_type == 'food_do_disease':
            desc = [i['m.name'] for i in answers]
            subject = answers[0]['n.name']
            final_answer = '患有{0}的人建议多试试{1}'.format('；'.join(list(set(desc))[:self.num_limit]), subject)

        elif question_type == 'disease_drug':
            desc = [i['n.name'] for i in answers]
            subject = answers[0]['m.name']
            final_answer = '{0}通常的使用的药品包括：{1}'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'drug_disease':
            desc = [i['m.name'] for i in answers]
            subject = answers[0]['n.name']
            final_answer = '{0}主治的疾病有{1},可以试试'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'disease_check':
            desc = [i['n.name'] for i in answers]
            subject = answers[0]['m.name']
            final_answer = '{0}通常可以通过以下方式检查出来：{1}'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        elif question_type == 'check_disease':
            desc = [i['m.name'] for i in answers]
            subject = answers[0]['n.name']
            final_answer = '通常可以通过{0}检查出来的疾病有{1}'.format(subject, '；'.join(list(set(desc))[:self.num_limit]))

        return final_answer

if __name__ == '__main__':
    searcher = AnswerSearcher()